
import sys


import re
_r = re.escape
def _re_replace(s : str, to_replace : dict):
    for p, r in to_replace.items():
        s = re.compile(p).sub(r, s)
    return s


import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline
%config InlineBackend.figure_formats = ['svg']


!{sys.executable} -m pip install --quiet pandas
import pandas as pd


!{sys.executable} -m pip install --quiet seaborn
import seaborn as sns


# OLS using statsmodels
!{sys.executable} -m pip install --quiet statsmodels numpy
import statsmodels.api as sm
import numpy as np

/opt/conda/lib/python3.9/site-packages/statsmodels/tsa/base/tsa_model.py:7: FutureWarning: pandas.Int64Index is deprecated and will be removed from pandas in a future version. Use pandas.Index with the appropriate dtype instead.
  from pandas import (to_datetime, Int64Index, DatetimeIndex, Period,
/opt/conda/lib/python3.9/site-packages/statsmodels/tsa/base/tsa_model.py:7: FutureWarning: pandas.Float64Index is deprecated and will be removed from pandas in a future version. Use pandas.Index with the appropriate dtype instead.
  from pandas import (to_datetime, Int64Index, DatetimeIndex, Period,


!{sys.executable} -m pip install --quiet sklearn
!{sys.executable} -m pip install --quiet patsy
import sklearn as skl

'''
!{sys.executable} -m pip install --quiet scikit-learn-intelex
import sklearnex as sklx
sklx.patch_sklearn()
'''

import sklearn.linear_model

from sklearn.compose import ColumnTransformer
from sklearn.datasets import fetch_openml
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import mean_squared_error
from sklearn.linear_model import Lasso
from sklearn.linear_model import ElasticNet
from sklearn.model_selection import KFold
import scipy.stats as stats
import patsy


_data_ = {
    name: pd.read_csv(
        file, 
        engine = 'c',
        low_memory = True,
        memory_map = False, # set `False` to load into memory
        **kwargs
    ) for name, file, kwargs in [
        ('appearances', 'data/appearances.csv', {
            'dtype': {
                'player_id': 'object',
                'game_id': 'object',
                'appearance_id': 'object',
                'competition_id': 'object',
                'player_club_id': 'object'
            }
        }),
        ('clubs', 'data/clubs.csv', {
            'dtype': {
                'club_id': 'object'
            }
        }),
        #('competitions', 'data/competitions.csv', {}),
        ('games', 'data/games.csv', {
            'dtype': {
                'game_id': 'object'
            }
        }),
        #('leagues', 'data/leagues.csv', {}),
        ('players', 'data/players.csv', {
            'parse_dates': ['date_of_birth'],
            'dtype': {
                'player_id': 'object',
                'country_of_birth': 'category',
                'country_of_citizenship': 'category',
                'position': 'category',
                'sub_position': 'category'
            }
        }),
        ('player_valuations', 'data/player_valuations.csv', {
            'parse_dates': ['date'],
            'dtype': {
                'player_id': 'object'
            }
        })
    ]
}


data = {}


# clubs
data['clubs'] = _data_['clubs'].copy()

data['clubs'] = data['clubs'][[
    'club_id', 
    'pretty_name'
]]
data['clubs'].rename(
    columns = {'pretty_name': 'club_name'},
    inplace = True
)
data['clubs'].set_index('club_id', inplace = True)

data['clubs']


# games
data['games'] = _data_['games'].copy()

data['games'] = data['games'][[
    'season', 
    'game_id'
]]
data['games'].set_index('game_id', inplace = True)

data['games']


# appearances
data['appearances'] = _data_['appearances'].copy()

data['appearances'] = data['appearances'].loc[
    :, ~data['appearances'].columns.isin([
        'appearance_id', 
        'competition_id'
    ])
]
data['appearances'].rename(
    columns = {'player_club_id': 'club_id'},
    inplace = True
)

data['appearances'] = (
    data['appearances']
        .merge(
            data['games'], 
            on = 'game_id',
            copy = False
        ).drop(columns = 'game_id')
        .merge(
            data['clubs'], 
            on = 'club_id',
            copy = False
        ).drop(columns = 'club_id')
)

data['appearances'] = (
    data['appearances']
        .groupby(['player_id', 'season'])
        .agg({
            **{
                c: 'sum' for c in [
                    'goals', 
                    'assists', 
                    'minutes_played', 
                    'yellow_cards', 
                    'red_cards'
                ]
            },
            'club_name': 'last'
        })
        .reset_index('season')
)

data['appearances']


# player valuations
data['player_valuations'] = _data_['player_valuations'].copy()

data['player_valuations']['season'] = (
    pd.DatetimeIndex(data['player_valuations']['date']).year
)
data['player_valuations'].drop(columns = 'date', inplace = True)

data['player_valuations'] = (
    data['player_valuations']
        .groupby(['player_id', 'season'])
        .agg({'market_value': 'mean'})
        .reset_index('season')
)
data['player_valuations'].rename(
    columns = {'market_value_in_gbp': 'market_value'},
    inplace = True
)

data['player_valuations']


# players
data['players'] = _data_['players'].copy()

data['players'] = data['players'].loc[
    :, ~data['players'].columns.isin([
        'last_season',
        'name',
        'current_club_id',
        'market_value_in_gbp',
        'highest_market_value_in_gbp',
        'country_of_birth',
        'url', 
        'foot'
    ])
]
data['players'].rename(
    columns = {
        'pretty_name': 'name',
        'height_in_cm': 'height',
        'country_of_citizenship': 'nationality'
    },
    inplace = True
)

data['players']['sub_position'] = (
    data['players']['sub_position'].cat
        .rename_categories(
            lambda s: (
                _re_replace(s, {
                    fr'''^(.*){_r(' - ')}(.*)$''': r'\2'
                })
                .title()
            )
        )
)

data['players'].set_index('player_id', inplace = True)

data['players']


# final dataset
data['all'] = data['players'].merge(
    data['player_valuations'].merge(
        data['appearances'], 
        on = ['player_id', 'season'],
        copy = False
    ), 
    on = 'player_id',
    copy = False
)

data['all']['age'] = (
    pd.to_datetime(data['all']['season'], format = '%Y', utc = True) 
        - pd.to_datetime(data['all']['date_of_birth'], utc = True)
).astype('timedelta64[Y]')
data['all'].drop(columns = 'date_of_birth', inplace = True)

data['all'].dropna(axis = 'index', inplace = True)

data['all']


data['all'][data['all'].isna().any(axis = 1)]


data['all'].dtypes

name                object
nationality       category
position          category
sub_position      category
height               int64
season               int64
market_value       float64
goals                int64
assists              int64
minutes_played       int64
yellow_cards         int64
red_cards            int64
club_name           object
age                float64
dtype: object


data['all'].describe()


pd.DataFrame(data['all']['sub_position'].unique())


data['all'][data['all']['name'] == 'Cristiano Ronaldo']


# one hot encode categorical features
data['all_onehot'] = pd.get_dummies(data['all'], columns = [
    'position', 
    'sub_position', 
    'nationality', 
    'club_name'
])

data['all_onehot']


data['all_onehot'].dtypes

name                              object
height                             int64
season                             int64
market_value                     float64
goals                              int64
                                  ...   
club_name_Yeni Malatyaspor         uint8
club_name_Zenit St Petersburg      uint8
club_name_Zirka Kropyvnytskyi      uint8
club_name_Zorya Lugansk            uint8
club_name_Zska Moskau              uint8
Length: 588, dtype: object


data['all_onehot'].describe()


data['all_onehot'][data['all_onehot']['name'] == 'Lionel Messi']


data['all_eda'] = data['all'].copy()

data['all_eda']['log_market_value'] = np.log(data['all_eda']['market_value'])


df_highest_market_value_players = data['all_eda'].nlargest(n = 1, columns = 'market_value')

df_highest_market_value_players


df_highest_market_value = data['all_eda'].loc[data['all_eda']['name'].isin(df_highest_market_value_players['name'])]

df_highest_market_value


_ = sns.barplot(
    data = df_highest_market_value, 
    x = 'season', y = 'market_value'
).set(title = 'Player Market Value Over the Years')
plt.xticks(rotation = 45, ha = 'right', rotation_mode = 'anchor')

plt.show()


_ = sns.displot(
    data = data['all_eda'].reset_index(), 
    x = 'market_value', 
    bins = 50
).set(title = 'Distribution of Market Values')

plt.show()


_ = sns.boxplot(data = data['all_eda'][[
    'goals',
    'assists',
    'yellow_cards',
    'red_cards'
]]).set(title = '')


_ = sns.histplot(
    data = data['all_eda'].reset_index(), x = 'height',
    bins = 100
).set(title = 'Distribution of Height')


corr = data['all_eda'].corr()
_ = sns.heatmap(corr,  
    cmap = 'seismic', 
    linewidth = 1, linecolor = 'white',
    vmax = 1, vmin = -1,
    mask = np.triu(np.ones_like(corr, dtype = bool)), 
    annot = True,
    fmt = '0.2f'
)


_ = sns.pairplot(data['all'][:1500].reset_index())


y, X = patsy.dmatrices('''
    market_value ~ 
        age + goals + assists + minutes_played 
            + yellow_cards + red_cards 
            + height + age
''', data=data['all_eda'], return_type="dataframe")
model = sm.OLS(y, X)
fit = model.fit()
pred = fit.predict(X)
fit.summary()


print((y))
print((pred))

np.sqrt(mean_squared_error((y),(pred)))

           market_value
player_id              
9800            90000.0
43084          360000.0
230826         360000.0
198087        1530000.0
110689          68000.0
...                 ...
364245         420000.0
364245        1102500.0
364245        5400000.0
575367         658250.0
575367         765000.0

[50781 rows x 1 columns]
player_id
9800     -5.312852e+05
43084    -4.060252e+05
230826    2.289005e+06
198087    5.058775e+06
110689    6.836034e+05
              ...     
364245    5.837390e+05
364245    6.375011e+06
364245    6.683061e+06
575367    9.031230e+05
575367    6.952160e+05
Length: 50781, dtype: float64

7309873.9471996445


data['all_eda']['log_market_value'] = np.log(data['all_eda']['market_value'])
y, X = patsy.dmatrices('''
    log_market_value ~ 
        age + goals + assists + minutes_played 
            + yellow_cards + red_cards 
            + height + age
''', data=data['all_eda'], return_type="dataframe")
model = sm.OLS(y, X)
fit = model.fit()
pred2 = fit.predict(X)
fit.summary()


print(np.exp(y))
print(np.exp(pred2))

np.sqrt(mean_squared_error((y),(pred2)))

           log_market_value
player_id                  
9800                90000.0
43084              360000.0
230826             360000.0
198087            1530000.0
110689              68000.0
...                     ...
364245             420000.0
364245            1102500.0
364245            5400000.0
575367             658250.0
575367             765000.0

[50781 rows x 1 columns]
player_id
9800      6.157680e+05
43084     4.928576e+05
230826    7.211031e+05
198087    1.931418e+06
110689    6.111676e+05
              ...     
364245    4.307993e+05
364245    2.970482e+06
364245    2.380843e+06
575367    4.402778e+05
575367    4.100153e+05
Length: 50781, dtype: float64

1.282369368429589


y, X = patsy.dmatrices('''
    log_market_value ~ 
        age + goals + assists + minutes_played 
            + yellow_cards + red_cards 
            + height + age 
            + C(nationality) + C(position) + C(sub_position) + C(club_name)
''', data=data['all_eda'], return_type="dataframe")
model = sm.OLS(y, X)
fit = model.fit()
pred3 = fit.predict(X)
fit.summary()


print(np.exp(y))
print(np.exp(pred3))

np.sqrt(mean_squared_error(y, pred3))

           log_market_value
player_id                  
9800                90000.0
43084              360000.0
230826             360000.0
198087            1530000.0
110689              68000.0
...                     ...
364245             420000.0
364245            1102500.0
364245            5400000.0
575367             658250.0
575367             765000.0

[50781 rows x 1 columns]
player_id
9800      1.742980e+05
43084     2.559757e+06
230826    8.474457e+05
198087    1.757640e+06
110689    9.412867e+04
              ...     
364245    9.750404e+05
364245    4.477367e+06
364245    3.204029e+06
575367    1.339464e+06
575367    1.307280e+06
Length: 50781, dtype: float64

0.8588668100888358


def diagnostic_plot(x, y):
    plt.figure(figsize=(20,5))
    
    rgr = LinearRegression()
    rgr.fit(x,y)
    pred = rgr.predict(x)

    plt.subplot(1, 3, 1)
    plt.scatter(pred,y,alpha=0.1)
    plt.plot(y, y, color='red',linewidth=1,)
    plt.title("Regression fit")
    plt.xlabel("Predicted y")
    plt.ylabel("y")
    
y = data['all_eda']['log_market_value']
X = data['all_eda'][[
    'goals', 
    'assists', 
    'minutes_played', 
    'yellow_cards', 
    'red_cards', 
    'height',
    'age'
   # 'nationality',
   # 'position',
   # 'sub_position',
   # 'club_name'
]]


sns.set(style='darkgrid')
diagnostic_plot(X, y)


y = data['all_eda']['market_value']
dataset = pd.get_dummies(data['all_eda'], columns = [
    'position', 
    'sub_position', 
    'nationality', 
    'club_name'
])

dataset = dataset.drop(columns = ['name','market_value'])

X_train, X_test, Y_train, Y_test = train_test_split(
    dataset, y, test_size = .30, random_state = 70)
    
regr = skl.linear_model.LinearRegression() 
# Do not use fit_intercept = False if you have removed 1 column after dummy encoding
regr.fit(X_train, Y_train)

predicted = regr.predict(X_test)

regr.score(X_test, Y_test)

-96149672.18314782


# feature selection
X = data['all'][[
    'goals', 
    'assists', 
    'minutes_played', 
    'yellow_cards', 
    'red_cards', 
    'height',
    'age',
    'season',
    'nationality',
    'position',
    'sub_position',
    'club_name'
]]
# labels
y = data['all']['market_value']


# numeric features
num_features = ['goals','assists','minutes_played', 'yellow_cards', 'red_cards', 'height','age']
num_transformer = Pipeline(
    steps=[("scaler", StandardScaler())]
)
categorical_features = ['nationality', 'position', 'sub_position', 'club_name']
cat_transformer = OneHotEncoder(handle_unknown='ignore')
preprocessor = ColumnTransformer(
    transformers=[
        ("num", num_transformer, num_features),
        ("cat", cat_transformer, categorical_features)]
)


# transform and create linear regression model
clf = Pipeline(
    steps=[("preprocessor", preprocessor), ("model", Lasso())]
)
# split our data, train on training data, and score on our test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
score

/opt/conda/lib/python3.9/site-packages/sklearn/linear_model/_coordinate_descent.py:513: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations. Duality gap: 3.329092090617099e+17, tolerance: 277502341864267.94
  model = cd_fast.sparse_enet_coordinate_descent(

0.5174926228911929


data['all']['predicted_market_value'] = np.exp(pred3)


data['all']

	club_name
club_id
1032	Fc Reading
2323	Orduspor
1387	Acn Siena 1904
3592	Kryvbas Kryvyi Rig
1071	Wigan Athletic
...	...
1269	Pec Zwolle
200	Fc Utrecht
317	Fc Twente Enschede
3948	Royale Union Saint Gilloise
1304	Heracles Almelo

	season
game_id
2244388	2012
2219794	2011
2244389	2012
2271112	2012
2229332	2012
...	...
3646190	2021
3646188	2021
3655616	2021
3655629	2021
3646191	2021

	season	goals	assists	minutes_played	yellow_cards	red_cards	club_name
player_id
10	2014	32	18	4578	12	0	Lazio Rom
10	2015	16	14	3428	6	0	Lazio Rom
100009	2014	0	0	5576	8	0	Kuban Krasnodar
100009	2015	2	2	4512	12	0	Kuban Krasnodar
100009	2016	0	0	1260	6	0	Anzhi Makhachkala
...	...	...	...	...	...	...	...
99923	2014	0	2	832	4	0	Cagliari Calcio
99924	2016	0	2	1824	6	0	Ca Osasuna
99977	2014	0	0	194	0	0	Rcd Mallorca
99977	2015	10	6	3046	2	0	Royal Excel Mouscron
99977	2019	0	0	716	0	0	Caykur Rizespor

	season	market_value
player_id
10	2004	6300000.0
10	2005	10800000.0
10	2006	22500000.0
10	2007	20700000.0
10	2008	18000000.0
...	...	...
99977	2018	990000.0
99977	2019	720000.0
99977	2020	562500.0
99977	2021	495000.0
99977	2022	540000.0

	name	nationality	date_of_birth	position	sub_position	height
player_id
254016	Arthur Delalande	France	1992-05-18	Midfield	Central Midfield	186
51053	Daniel Davari	Iran	1988-01-06	Goalkeeper	Goalkeeper	192
31451	Torsten Oehrl	Germany	1986-01-07	Attack	Centre-Forward	192
44622	Vladimir Kisenkov	Russia	1981-10-08	Defender	Right-Back	182
30802	Oscar Diaz	Spain	1984-04-24	Attack	Centre-Forward	183
...	...	...	...	...	...	...
462285	Fabian De Keijzer	Netherlands	2000-05-10	Goalkeeper	Goalkeeper	193
368612	Merveille Bokadi	DR Congo	1996-05-21	Defender	Centre-Back	186
408574	Joey Veerman	Netherlands	1998-11-19	Midfield	Central Midfield	185
364245	Jordan Teze	Netherlands	1999-09-30	Defender	Centre-Back	183
575367	Richard Ledezma	United States	2000-09-06	Attack	Attacking Midfield	174

COGS 118A - Final Project¶

Group members¶

Abstract¶

Background¶

Problem Statement¶

Data¶

Evaluation¶

One hot encoding¶

Exploratory Data Analysis¶

Proposed Solution¶

Evaluation Metrics¶

Results¶

Subsection 1¶

Subsection 2¶

Subsection 3¶

Subsection 4¶

Discussion¶

Limitations¶

Ethics & Privacy¶

Conclusion¶

Footnotes¶

	name	nationality	position	sub_position	height	season	market_value	goals	assists	minutes_played	yellow_cards	red_cards	club_name	age
player_id
9800	Artem Milevskyi	Ukraine	Attack	Centre-Forward	189	2020	90000.0	0	0	720	6	0	Fk Minaj	34.0
43084	Gaetano Berardi	Switzerland	Defender	Right-Back	179	2020	360000.0	0	0	228	0	0	Leeds United	31.0
230826	Gennaro Acampora	Italy	Midfield	Central Midfield	174	2020	360000.0	2	4	1248	4	0	Spezia Calcio	25.0
198087	Matteo Ricci	Italy	Midfield	Defensive Midfield	176	2020	1530000.0	0	6	4880	10	0	Spezia Calcio	25.0
110689	Deniz Mehmet	Turkey	Goalkeeper	Goalkeeper	192	2020	68000.0	0	0	1080	0	0	Dundee United Fc	27.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
364245	Jordan Teze	Netherlands	Defender	Centre-Back	183	2019	420000.0	0	0	360	0	0	Psv Eindhoven	19.0
364245	Jordan Teze	Netherlands	Defender	Centre-Back	183	2020	1102500.0	0	2	7494	10	0	Psv Eindhoven	20.0
364245	Jordan Teze	Netherlands	Defender	Centre-Back	183	2021	5400000.0	2	8	5260	12	0	Psv Eindhoven	21.0
575367	Richard Ledezma	United States	Attack	Attacking Midfield	174	2020	658250.0	0	2	234	2	0	Psv Eindhoven	19.0
575367	Richard Ledezma	United States	Attack	Attacking Midfield	174	2021	765000.0	2	0	88	0	0	Psv Eindhoven	20.0

	height	season	market_value	goals	assists	minutes_played	yellow_cards	red_cards	age
count	50781.000000	50781.000000	5.078100e+04	50781.000000	50781.000000	50781.000000	50781.000000	50781.000000	50781.000000
mean	180.794628	2017.380063	3.630890e+06	3.880546	2.949883	2805.795987	6.001575	0.143243	24.655284
std	17.703409	2.318805	8.274637e+06	7.352176	4.793814	2103.361660	6.095317	0.543827	4.375994
min	0.000000	2013.000000	9.000000e+03	0.000000	0.000000	2.000000	0.000000	0.000000	14.000000
25%	178.000000	2015.000000	3.600000e+05	0.000000	0.000000	884.000000	2.000000	0.000000	21.000000
50%	182.000000	2017.000000	9.000000e+05	0.000000	2.000000	2566.000000	4.000000	0.000000	24.000000
75%	187.000000	2019.000000	3.150000e+06	4.000000	4.000000	4410.000000	10.000000	0.000000	28.000000
max	206.000000	2021.000000	1.800000e+08	122.000000	62.000000	10122.000000	46.000000	6.000000	42.000000

	name	nationality	position	sub_position	height	season	market_value	goals	assists	minutes_played	yellow_cards	red_cards	club_name	age
player_id
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2014	96000000.0	122	46	9282	12	2	Real Madrid	28.0
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2015	105000000.0	102	30	8586	6	0	Real Madrid	29.0
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2016	99000000.0	84	24	8252	10	0	Real Madrid	30.0
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2017	90000000.0	88	16	7356	10	0	Real Madrid	31.0
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2018	96000000.0	56	20	7292	8	2	Juventus Turin	32.0
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2019	74250000.0	70	14	7982	6	0	Juventus Turin	33.0
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2020	54000000.0	76	8	7682	10	0	Juventus Turin	34.0
8198	Cristiano Ronaldo	Portugal	Attack	Centre-Forward	187	2021	39000000.0	48	6	6202	20	0	Juventus Turin	35.0

	name	height	season	market_value	goals	assists	minutes_played	yellow_cards	red_cards	age	...	club_name_West Bromwich Albion	club_name_West Ham United	club_name_Wigan Athletic	club_name_Willem Ii Tilburg	club_name_Wolverhampton Wanderers	club_name_Yeni Malatyaspor	club_name_Zenit St Petersburg	club_name_Zirka Kropyvnytskyi	club_name_Zorya Lugansk	club_name_Zska Moskau
player_id
28003	Lionel Messi	169	2014	108000000.0	116	62	10122	12	0	26.0	...	0	0	0	0	0	0	0	0	0	0
28003	Lionel Messi	169	2015	108000000.0	82	48	8458	10	0	27.0	...	0	0	0	0	0	0	0	0	0	0
28003	Lionel Messi	169	2016	108000000.0	108	40	8904	18	0	28.0	...	0	0	0	0	0	0	0	0	0	0
28003	Lionel Messi	169	2017	108000000.0	90	40	8936	14	0	29.0	...	0	0	0	0	0	0	0	0	0	0
28003	Lionel Messi	169	2018	156000000.0	102	44	8048	6	0	30.0	...	0	0	0	0	0	0	0	0	0	0
28003	Lionel Messi	169	2019	130500000.0	60	50	7262	14	0	31.0	...	0	0	0	0	0	0	0	0	0	0
28003	Lionel Messi	169	2020	95400000.0	78	30	8746	12	2	32.0	...	0	0	0	0	0	0	0	0	0	0
28003	Lionel Messi	169	2021	66000000.0	22	26	5384	2	0	33.0	...	0	0	0	0	0	0	0	0	0	0

	name	nationality	position	sub_position	height	season	market_value	goals	assists	minutes_played	yellow_cards	red_cards	club_name	age	log_market_value
player_id
342229	Kylian Mbappe	France	Attack	Centre-Forward	178	2019	180000000.0	48	24	4102	4	0	Fc Paris Saint Germain	20.0	19.008467

Dep. Variable:	market_value	R-squared:	0.220
Model:	OLS	Adj. R-squared:	0.219
Method:	Least Squares	F-statistic:	2041.
Date:	Fri, 10 Jun 2022	Prob (F-statistic):	0.00
Time:	03:39:42	Log-Likelihood:	-8.7464e+05
No. Observations:	50781	AIC:	1.749e+06
Df Residuals:	50773	BIC:	1.749e+06
Df Model:	7
Covariance Type:	nonrobust

	coef	std err	t	P>\|t\|	[0.025	0.975]
Intercept	1.938e+05	3.77e+05	0.514	0.607	-5.45e+05	9.33e+05
age	-7.077e+04	7609.677	-9.300	0.000	-8.57e+04	-5.59e+04
goals	2.389e+05	5556.790	42.994	0.000	2.28e+05	2.5e+05
assists	3.135e+05	8922.514	35.136	0.000	2.96e+05	3.31e+05
minutes_played	826.8657	22.786	36.288	0.000	782.205	871.526
yellow_cards	-6.638e+04	6910.754	-9.606	0.000	-7.99e+04	-5.28e+04
red_cards	-7.781e+04	6.05e+04	-1.287	0.198	-1.96e+05	4.07e+04
height	7851.4099	1846.711	4.252	0.000	4231.837	1.15e+04

Omnibus:	53530.739	Durbin-Watson:	0.636
Prob(Omnibus):	0.000	Jarque-Bera (JB):	5620986.518
Skew:	5.193	Prob(JB):	0.00
Kurtosis:	53.485	Cond. No.	4.08e+04

Dep. Variable:	log_market_value	R-squared:	0.282
Model:	OLS	Adj. R-squared:	0.282
Method:	Least Squares	F-statistic:	2851.
Date:	Fri, 10 Jun 2022	Prob (F-statistic):	0.00
Time:	03:39:42	Log-Likelihood:	-84685.
No. Observations:	50781	AIC:	1.694e+05
Df Residuals:	50773	BIC:	1.695e+05
Df Model:	7
Covariance Type:	nonrobust

Omnibus:	836.100	Durbin-Watson:	0.853
Prob(Omnibus):	0.000	Jarque-Bera (JB):	794.667
Skew:	0.271	Prob(JB):	2.76e-173
Kurtosis:	2.716	Cond. No.	4.08e+04

	coef	std err	t	P>\|t\|	[0.025	0.975]
Intercept	11.7302	0.066	177.262	0.000	11.600	11.860
age	0.0156	0.001	11.664	0.000	0.013	0.018
goals	0.0231	0.001	23.713	0.000	0.021	0.025
assists	0.0473	0.002	30.198	0.000	0.044	0.050
minutes_played	0.0003	4e-06	63.609	0.000	0.000	0.000
yellow_cards	0.0007	0.001	0.560	0.576	-0.002	0.003
red_cards	0.0093	0.011	0.880	0.379	-0.011	0.030
height	0.0047	0.000	14.436	0.000	0.004	0.005

	coef	std err	t	P>\|t\|	[0.025	0.975]
Intercept	11.2022	0.559	20.054	0.000	10.107	12.297
C(nationality)[T.Albania]	0.0602	0.622	0.097	0.923	-1.159	1.280
C(nationality)[T.Algeria]	0.2460	0.621	0.396	0.692	-0.972	1.463
C(nationality)[T.Angola]	0.3028	0.625	0.485	0.628	-0.922	1.527
C(nationality)[T.Antigua and Barbuda]	0.2055	0.714	0.288	0.774	-1.194	1.606
C(nationality)[T.Argentina]	0.2909	0.620	0.470	0.639	-0.924	1.505
C(nationality)[T.Armenia]	-0.0123	0.626	-0.020	0.984	-1.238	1.214
C(nationality)[T.Aruba]	-0.0934	0.652	-0.143	0.886	-1.372	1.185
C(nationality)[T.Australia]	0.1484	0.622	0.239	0.811	-1.071	1.368
C(nationality)[T.Austria]	0.2672	0.621	0.430	0.667	-0.950	1.484
C(nationality)[T.Azerbaijan]	-0.1249	0.643	-0.194	0.846	-1.386	1.136
C(nationality)[T.Bahrain]	1.212e-12	1.44e-12	0.842	0.400	-1.61e-12	4.03e-12
C(nationality)[T.Barbados]	2.792e-13	9.28e-13	0.301	0.764	-1.54e-12	2.1e-12
C(nationality)[T.Belarus]	0.0540	0.625	0.086	0.931	-1.170	1.278
C(nationality)[T.Belgium]	0.1501	0.619	0.242	0.808	-1.064	1.364
C(nationality)[T.Benin]	-0.0736	0.633	-0.116	0.907	-1.315	1.168
C(nationality)[T.Bermuda]	0.8495	1.065	0.798	0.425	-1.238	2.937
C(nationality)[T.Bolivia]	0.2664	0.665	0.401	0.689	-1.037	1.570
C(nationality)[T.Bosnia-Herzegovina]	0.1182	0.621	0.190	0.849	-1.099	1.336
C(nationality)[T.Brazil]	0.2350	0.619	0.379	0.704	-0.979	1.449
C(nationality)[T.Bulgaria]	0.1903	0.626	0.304	0.761	-1.036	1.416
C(nationality)[T.Burkina Faso]	0.2280	0.625	0.365	0.715	-0.998	1.454
C(nationality)[T.Burundi]	0.3019	0.656	0.460	0.645	-0.984	1.588
C(nationality)[T.Cameroon]	0.2571	0.621	0.414	0.679	-0.959	1.474
C(nationality)[T.Canada]	-0.0476	0.626	-0.076	0.939	-1.275	1.180
C(nationality)[T.Cape Verde]	0.1084	0.623	0.174	0.862	-1.113	1.330
C(nationality)[T.Central African Republic]	0.4384	0.647	0.677	0.498	-0.831	1.707
C(nationality)[T.Chad]	0.1484	0.665	0.223	0.823	-1.155	1.451
C(nationality)[T.Chile]	0.2310	0.623	0.371	0.711	-0.991	1.453
C(nationality)[T.China]	-0.4184	0.656	-0.638	0.524	-1.704	0.867
C(nationality)[T.Chinese Taipei (Taiwan)]	-0.7057	0.761	-0.927	0.354	-2.198	0.786
C(nationality)[T.Colombia]	0.4487	0.621	0.723	0.470	-0.768	1.666
C(nationality)[T.Comoros]	0.3576	0.641	0.558	0.577	-0.898	1.613
C(nationality)[T.Congo]	0.1482	0.626	0.237	0.813	-1.080	1.376
C(nationality)[T.Costa Rica]	0.1354	0.627	0.216	0.829	-1.093	1.363
C(nationality)[T.Cote d'Ivoire]	0.3575	0.620	0.576	0.564	-0.858	1.573
C(nationality)[T.Croatia]	0.3805	0.620	0.614	0.539	-0.835	1.596
C(nationality)[T.Cuba]	-0.0300	1.067	-0.028	0.978	-2.121	2.061
C(nationality)[T.Curacao]	-0.0399	0.626	-0.064	0.949	-1.267	1.187

Omnibus:	2497.905	Durbin-Watson:	1.351
Prob(Omnibus):	0.000	Jarque-Bera (JB):	3773.239
Skew:	-0.442	Prob(JB):	0.00
Kurtosis:	4.001	Cond. No.	2.37e+19